Towards Expressive Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis
Previous works on expressive speech synthesis mainly focus on current sentence. The context in adjacent sentences is neglected, resulting in inflexible speaking style for the same text, which lacks speech variations. In this paper, we propose a hierarchical framework to model speaking style from context. A hierarchical context encoder is proposed to explore a wider range of contextual information considering structural relationship in context, including inter-phrase and inter-sentence relations. Moreover, to encourage this encoder to learn style representation better, we introduce a novel training strategy with knowledge distillation, which provides the target for encoder training. Both objective and subjective evaluations on a Mandarin lecture dataset demonstrate that the proposed method can significantly improve the naturalness and expressiveness of the synthesized speech.
Code (0)
등록된 구현이 없습니다.
Tasks
Expressive Speech SynthesisKnowledge DistillationSentenceSpeech SynthesisSimilar Papers 제목 키워드 기반
Unsupervised Multi-scale Expressive Speaking Style Modeling with Hierarchical Context Information for Audiobook Speech Synthesis
Naturalness and expressiveness are crucial for audiobook speech synthesis, but now are limited by the averaged global-scale speaking style representation. In this paper, we propose an unsupervised multi-scale context-sen…
Speech Synthesistext-to-speechText to SpeechExpressive Text-to-Speech using Style Tag
As recent text-to-speech (TTS) systems have been rapidly improved in speech quality and generation speed, many researchers now focus on a more challenging issue: expressive TTS. To control speaking styles, existing expre…
Language ModelingLanguage ModellingTAGtext-to-speech+1Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis
This paper proposes a hierarchical generative model with a multi-grained latent variable to synthesize expressive speech. In recent years, fine-grained latent variables are introduced into the text-to-speech synthesis th…
Expressive Speech SynthesisSpeech Synthesistext-to-speechText to Speech+1Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesis
Global Style Tokens (GSTs) are a recently-proposed method to learn latent disentangled representations of high-dimensional data. GSTs can be used within Tacotron, a state-of-the-art end-to-end text-to-speech synthesis sy…
Speech Synthesistext-to-speechText to SpeechText-To-Speech SynthesisExpressive Speech Retrieval using Natural Language Descriptions of Speaking Style
We introduce the task of expressive speech retrieval, where the goal is to retrieve speech utterances spoken in a given style based on a natural language description of that style. While prior work has primarily focused …